Nonlinear growth models represent an instance of nonlinear regression models, a class of models taking the general form \[ y = \mu(x, \theta) + \epsilon, \] where \(\mu(x, \theta)\) is the mean function which depends on a possibly vector-valued parameter \(\theta\), and a possibly vector-valued predictor \(x\). The stochastic component \(\epsilon\) represents the error with mean zero and constant variance. Usually, a Gaussian distribution is also assumed for the error term.
By defining the mean function \(\mu(x, \theta)\) we may obtain several different models, all characterized by the fact that parameters \(\theta\) enter in a nonlinear way into the equation. Parameters are usually estimated by nonlinear least squares which aims at minimizing the residual sum of squares.
\[ \mu(x) = \theta_1 \exp\{\theta_2 x\} \] where \(\theta_1\) is the value at the origin (i.e. \(\mu(x=0)\)), and \(\theta_2\) represents the (constant) relative ratio of change (i.e. \(\frac{d\mu(x)}{dx }\frac{1}{\mu(x)} = \theta_2\)). Thus, the model describes an increasing (exponential growth if \(\theta_2 > 0\)) or decreasing (exponential decay if \(\theta_2 < 0\)) trend with constant relative rate.
\[ \mu(x) = \frac{\theta_1}{1+\exp\{(\theta_2 - x)/\theta_3\}} \] where \(\theta_1\) is the upper horizontal asymptote, \(\theta_2\) represents the x-value at the inflection point of the symmetric growth curve, and \(\theta_3\) represents a scale parameter (and \(1/\theta_3\) is the growth-rate parameter that controls how quickly the curve approaches the upper asymptote).
\[ \mu(x) = \theta_1 \exp\{-\theta_2 \theta_3^x\} \] where \(\theta_1\) is the horizontal asymptote, \(\theta_2\) represents the value of the function at \(x = 0\) (displacement along the x-axis), and \(\theta_3\) represents a scale parameter.
The difference between the logistic and Gompertz functions is that the latter is not symmetric around the inflection point.
\[ \mu(x) = \theta_1 (1 - \exp\{-\theta_2 x\})^{\theta_3} \] where \(\theta_1\) is the horizontal asymptote, \(\theta_2\) represents the rate of growth, and \(\theta_3\) in part determines the point of inflection on the y-axis.
Dipartimento della Protezione Civile: COVID-19 Italia - Monitoraggio della situazione http://arcg.is/C1unv
Source: https://github.com/pcm-dpc/COVID-19
url = "https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-andamento-nazionale/dpc-covid19-ita-andamento-nazionale.csv"
COVID19 <- read.csv(file = url, stringsAsFactors = FALSE)
COVID19$data <- as.Date(COVID19$data)
# DT::datatable(COVID19)Warnings
- 29/03/2020: dati Regione Emilia Romagna parziali (dato tampone non aggiornato).
- 26/03/2020: dati Regione Piemonte parziali (-50 deceduti - comunicazione tardiva)
- 18/03/2020: dati Regione Campania non pervenuti.
- 18/03/2020: dati Provincia di Parma non pervenuti.
- 17/03/2020: dati Provincia di Rimini non aggiornati
- 16/03/2020: dati P.A. Trento e Puglia non pervenuti.
- 11/03/2020: dati Regione Abruzzo non pervenuti.
- 10/03/2020: dati Regione Lombardia parziali.
- 07/03/2020: dati Brescia +300 esiti positivi
# create data for analysis
data = data.frame(date = COVID19$data,
y = COVID19$totale_casi,
dy = reldiff(COVID19$totale_casi))
data$x = as.numeric(data$date) - min(as.numeric(data$date)) + 1
DT::datatable(data, options = list("pageLength" = 5))mod1_start = lm(log(y) ~ x, data = data)
b = unname(coef(mod1_start))
start = list(th1 = exp(b[1]), th2 = b[2])
exponential <- function(x, th1, th2) th1 * exp(th2 * x)
mod1 = nls(y ~ exponential(x, th1, th2), data = data, start = start)
summary(mod1)
##
## Formula: y ~ exponential(x, th1, th2)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## th1 11598.256912 1467.689109 7.902 0.000000000236 ***
## th2 0.054283 0.002855 19.012 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15030 on 50 degrees of freedom
##
## Number of iterations to convergence: 12
## Achieved convergence tolerance: 0.000003896mod2 = nls(y ~ SSlogis(x, Asym, xmid, scal), data = data)
summary(mod2)
##
## Formula: y ~ SSlogis(x, Asym, xmid, scal)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## Asym 169723.0525 2199.6781 77.16 <2e-16 ***
## xmid 33.1702 0.2716 122.13 <2e-16 ***
## scal 6.9938 0.1714 40.79 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2908 on 49 degrees of freedom
##
## Number of iterations to convergence: 0
## Achieved convergence tolerance: 0.000002085mod3 = nls(y ~ SSgompertz(x, Asym, b2, b3), data = data)
# start = list(Asym = coef(mod2)[1])
# tmp = list(y = log(log(start$Asym) - log(data$y)), x = data$x)
# b = unname(coef(lm(y ~ x, data = tmp)))
# start = c(start, c(b2 = exp(b[1]), b3 = exp(b[2])))
# mod3 = nls(y ~ SSgompertz(x, Asym, b2, b3), data = data, start = start,
# control = nls.control(maxiter = 1000))
summary(mod3)
##
## Formula: y ~ SSgompertz(x, Asym, b2, b3)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## Asym 205203.6473571 1991.2293501 103.05 <2e-16 ***
## b2 9.5014920 0.2044561 46.47 <2e-16 ***
## b3 0.9305064 0.0009424 987.42 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1124 on 49 degrees of freedom
##
## Number of iterations to convergence: 1
## Achieved convergence tolerance: 0.0000005659richards <- function(x, th1, th2, th3) th1*(1 - exp(-th2*x))^th3
Loss <- function(th, y, x) sum((y - richards(x, th[1], th[2], th[3]))^2)
start <- optim(par = c(coef(mod2)[1], 0.001, 1), fn = Loss,
y = data$y, x = data$x)$par
names(start) <- c("th1", "th2", "th3")
mod4 = nls(y ~ richards(x, th1, th2, th3), data = data, start = start,
# trace = TRUE, algorithm = "plinear",
control = nls.control(maxiter = 1000, tol = 0.1))
# algorithm is not converging...
summary(mod4)
##
## Formula: y ~ richards(x, th1, th2, th3)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## th1 216826.22303 3230.96340 67.11 <2e-16 ***
## th2 0.06195 0.00146 42.43 <2e-16 ***
## th3 6.75388 0.23364 28.91 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1285 on 49 degrees of freedom
##
## Number of iterations to convergence: 3
## Achieved convergence tolerance: 0.01878
# library(nlmrt)
# mod4 = nlxb(y ~ th1*(1 - exp(-th2*x))^th3,
# data = data, start = start, trace = TRUE)models = list("Exponential model" = mod1,
"Logistic model" = mod2,
"Gompertz model" = mod3,
"Richards model" = mod4)
tab = data.frame(loglik = sapply(models, logLik),
df = sapply(models, function(m) attr(logLik(m), "df")),
Rsquare = sapply(models, function(m)
cor(data$y, fitted(m))^2),
AIC = sapply(models, AIC),
AICc = sapply(models, AICc),
BIC = sapply(models, BIC))
sel <- apply(tab[,4:6], 2, which.min)
tab$"" <- sapply(tabulate(sel, nbins = length(models))+1, symnum,
cutpoints = 0:4, symbols = c("", "*", "**", "***"))
knitr::kable(tab)| loglik | df | Rsquare | AIC | AICc | BIC | ||
|---|---|---|---|---|---|---|---|
| Exponential model | -572.8847 | 3 | 0.9418809 | 1151.7695 | 1152.2695 | 1157.6232 | |
| Logistic model | -486.9601 | 4 | 0.9978781 | 981.9201 | 982.7712 | 989.7251 | |
| Gompertz model | -437.5293 | 4 | 0.9996506 | 883.0586 | 883.9096 | 890.8635 | *** |
| Richards model | -444.4784 | 4 | 0.9995877 | 896.9568 | 897.8078 | 904.7617 |
ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(aes(y = fitted(mod1), color = "Exponential")) +
geom_line(aes(y = fitted(mod2), color = "Logistic")) +
geom_line(aes(y = fitted(mod3), color = "Gompertz")) +
geom_line(aes(y = fitted(mod4), color = "Richards")) +
labs(x = "", y = "Infected", color = "Model") +
scale_color_manual(values = cols) +
scale_y_continuous(breaks = seq(0, coef(mod2)[1], by = 10000),
minor_breaks = seq(0, coef(mod2)[1], by = 5000)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))last_plot() +
scale_y_continuous(trans = "log10", limits = c(100,NA)) +
labs(y = "Infected (log10 scale)")df = data.frame(x = seq(min(data$x), max(data$x)+14))
df = cbind(df, date = as.Date(df$x, origin = data$date[1]-1),
fit1 = predict(mod1, newdata = df),
fit2 = predict(mod2, newdata = df),
fit3 = predict(mod3, newdata = df),
fit4 = predict(mod4, newdata = df))
ylim = c(0, max(df[,c("fit2", "fit3")]))ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(data = df, aes(x = date, y = fit1, color = "Exponential")) +
geom_line(data = df, aes(x = date, y = fit2, color = "Logistic")) +
geom_line(data = df, aes(x = date, y = fit3, color = "Gompertz")) +
geom_line(data = df, aes(x = date, y = fit4, color = "Richards")) +
coord_cartesian(ylim = ylim) +
labs(x = "", y = "Infected", color = "Model") +
scale_y_continuous(breaks = seq(0, max(ylim), by = 10000),
minor_breaks = seq(0, max(ylim), by = 5000)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
scale_color_manual(values = cols) +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))# compute prediction using Moving Block Bootstrap (MBB) for nls
df = data.frame(x = seq(min(data$x), max(data$x)+14))
df = cbind(df, date = as.Date(df$x, origin = data$date[1]-1))
pred1 = cbind(df, "fit" = predict(mod1, newdata = df))
pred1[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod1, df[df$x > max(data$x),])[,2:3]
pred2 = cbind(df, "fit" = predict(mod2, newdata = df))
pred2[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod2, df[df$x > max(data$x),])[,2:3]
pred3 = cbind(df, "fit" = predict(mod3, newdata = df))
pred3[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod3, df[df$x > max(data$x),])[,2:3]
pred4 = cbind(df, "fit" = predict(mod4, newdata = df))
pred4[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod4, df[df$x > max(data$x),])[,2:3]
# predictions for next day
pred = rbind(subset(pred1, x == max(data$x)+1, select = 2:5),
subset(pred2, x == max(data$x)+1, select = 2:5),
subset(pred3, x == max(data$x)+1, select = 2:5),
subset(pred4, x == max(data$x)+1, select = 2:5))
print(pred, digits = 3)
## date fit lwr upr
## 53 2020-04-16 205992 165875 248673
## 531 2020-04-16 160313 152921 166170
## 532 2020-04-16 166519 163705 169350
## 533 2020-04-16 167491 164641 171256
ylim = c(0, max(pred2$upr, pred3$upr, na.rm=TRUE))ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(data = pred1, aes(x = date, y = fit, color = "Exponential")) +
geom_line(data = pred2, aes(x = date, y = fit, color = "Logistic")) +
geom_line(data = pred3, aes(x = date, y = fit, color = "Gompertz")) +
geom_line(data = pred4, aes(x = date, y = fit, color = "Richards")) +
geom_ribbon(data = pred1, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[1], alpha=0.3) +
geom_ribbon(data = pred2, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[2], alpha=0.3) +
geom_ribbon(data = pred3, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[3], alpha=0.3) +
geom_ribbon(data = pred4, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[4], alpha=0.3) +
coord_cartesian(ylim = c(0, max(ylim))) +
labs(x = "", y = "Infected", color = "Model") +
scale_y_continuous(minor_breaks = seq(0, max(ylim), by = 10000)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
scale_color_manual(values = cols) +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))# create data for analysis
data = data.frame(date = COVID19$data,
y = COVID19$deceduti,
dy = reldiff(COVID19$deceduti))
data$x = as.numeric(data$date) - min(as.numeric(data$date)) + 1
DT::datatable(data, options = list("pageLength" = 5))mod1_start = lm(log(y) ~ x, data = data)
b = unname(coef(mod1_start))
start = list(th1 = exp(b[1]), th2 = b[2])
exponential <- function(x, th1, th2) th1 * exp(th2 * x)
mod1 = nls(y ~ exponential(x, th1, th2), data = data, start = start)
summary(mod1)
##
## Formula: y ~ exponential(x, th1, th2)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## th1 995.457328 141.694274 7.025 0.00000000548 ***
## th2 0.062269 0.003148 19.778 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1810 on 50 degrees of freedom
##
## Number of iterations to convergence: 12
## Achieved convergence tolerance: 0.00000829mod2 = nls(y ~ SSlogis(x, Asym, xmid, scal), data = data)
summary(mod2)
##
## Formula: y ~ SSlogis(x, Asym, xmid, scal)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## Asym 22424.7598 264.1018 84.91 <2e-16 ***
## xmid 35.7571 0.2207 162.03 <2e-16 ***
## scal 6.4043 0.1342 47.73 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 304.7 on 49 degrees of freedom
##
## Number of iterations to convergence: 0
## Achieved convergence tolerance: 0.000002502mod3 = nls(y ~ SSgompertz(x, Asym, b2, b3), data = data)
# manually set starting values
# start = list(Asym = coef(mod2)[1])
# tmp = list(y = log(log(start$Asym) - log(data$y)), x = data$x)
# b = unname(coef(lm(y ~ x, data = tmp)))
# start = c(start, c(b2 = exp(b[1]), b3 = exp(b[2])))
# mod3 = nls(y ~ SSgompertz(x, Asym, b2, b3), data = data, start = start,
# control = nls.control(maxiter = 10000))
summary(mod3)
##
## Formula: y ~ SSgompertz(x, Asym, b2, b3)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## Asym 27860.9956268 244.7450806 113.84 <2e-16 ***
## b2 13.6787949 0.2937633 46.56 <2e-16 ***
## b3 0.9267856 0.0008312 1114.96 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 111.9 on 49 degrees of freedom
##
## Number of iterations to convergence: 0
## Achieved convergence tolerance: 0.000002781richards <- function(x, th1, th2, th3) th1*(1 - exp(-th2*x))^th3
Loss <- function(th, y, x) sum((y - richards(x, th[1], th[2], th[3]))^2)
start <- optim(par = c(coef(mod2)[1], 0.001, 1), fn = Loss,
y = data$y, x = data$x)$par
names(start) <- c("th1", "th2", "th3")
mod4 = nls(y ~ richards(x, th1, th2, th3), data = data, start = start,
# trace = TRUE, algorithm = "port",
control = nls.control(maxiter = 1000))
summary(mod4)
##
## Formula: y ~ richards(x, th1, th2, th3)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## th1 28961.576921 373.840335 77.47 <2e-16 ***
## th2 0.068849 0.001285 53.56 <2e-16 ***
## th3 10.552266 0.350687 30.09 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 133.5 on 49 degrees of freedom
##
## Number of iterations to convergence: 2
## Achieved convergence tolerance: 0.000002939models = list("Exponential model" = mod1,
"Logistic model" = mod2,
"Gompertz model" = mod3,
"Richards model" = mod4)
tab = data.frame(loglik = sapply(models, logLik),
df = sapply(models, function(m) attr(logLik(m), "df")),
Rsquare = sapply(models, function(m)
cor(data$y, fitted(m))^2),
AIC = sapply(models, AIC),
AICc = sapply(models, AICc),
BIC = sapply(models, BIC))
sel <- apply(tab[,4:6], 2, which.min)
tab$"" <- sapply(tabulate(sel, nbins = length(models))+1, symnum,
cutpoints = 0:4, symbols = c("", "*", "**", "***"))
knitr::kable(tab)| loglik | df | Rsquare | AIC | AICc | BIC | ||
|---|---|---|---|---|---|---|---|
| Exponential model | -462.8113 | 3 | 0.9511399 | 931.6226 | 932.1226 | 937.4763 | |
| Logistic model | -369.6415 | 4 | 0.9986695 | 747.2830 | 748.1341 | 755.0880 | |
| Gompertz model | -317.5528 | 4 | 0.9997984 | 643.1055 | 643.9566 | 650.9105 | *** |
| Richards model | -326.7188 | 4 | 0.9997288 | 661.4376 | 662.2887 | 669.2426 |
ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(aes(y = fitted(mod1), color = "Exponential")) +
geom_line(aes(y = fitted(mod2), color = "Logistic")) +
geom_line(aes(y = fitted(mod3), color = "Gompertz")) +
geom_line(aes(y = fitted(mod4), color = "Richards")) +
labs(x = "", y = "Deceased", color = "Model") +
scale_color_manual(values = cols) +
scale_y_continuous(breaks = seq(0, coef(mod2)[1], by = 1000),
minor_breaks = seq(0, coef(mod2)[1], by = 500)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))last_plot() +
scale_y_continuous(trans = "log10", limits = c(10,NA)) +
labs(y = "Deceased (log10 scale)")df = data.frame(x = seq(min(data$x), max(data$x)+14))
df = cbind(df, date = as.Date(df$x, origin = data$date[1]-1),
fit1 = predict(mod1, newdata = df),
fit2 = predict(mod2, newdata = df),
fit3 = predict(mod3, newdata = df),
fit4 = predict(mod4, newdata = df))
ylim = c(0, max(df[,-(1:3)]))ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(data = df, aes(x = date, y = fit1, color = "Exponential")) +
geom_line(data = df, aes(x = date, y = fit2, color = "Logistic")) +
geom_line(data = df, aes(x = date, y = fit3, color = "Gompertz")) +
geom_line(data = df, aes(x = date, y = fit4, color = "Richards")) +
coord_cartesian(ylim = ylim) +
labs(x = "", y = "Deceased", color = "Model") +
scale_y_continuous(breaks = seq(0, max(ylim), by = 1000),
minor_breaks = seq(0, max(ylim), by = 1000)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
scale_color_manual(values = cols) +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))# compute prediction using Moving Block Bootstrap (MBB) for nls
df = data.frame(x = seq(min(data$x), max(data$x)+14))
df = cbind(df, date = as.Date(df$x, origin = data$date[1]-1))
pred1 = cbind(df, "fit" = predict(mod1, newdata = df))
pred1[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod1, df[df$x > max(data$x),])[,2:3]
pred2 = cbind(df, "fit" = predict(mod2, newdata = df))
pred2[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod2, df[df$x > max(data$x),])[,2:3]
pred3 = cbind(df, "fit" = predict(mod3, newdata = df))
pred3[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod3, df[df$x > max(data$x),])[,2:3]
pred4 = cbind(df, "fit" = predict(mod4, newdata = df))
pred4[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod4, df[df$x > max(data$x),])[,2:3]
# predictions for next day
pred = rbind(subset(pred1, x == max(data$x)+1, select = 2:5),
subset(pred2, x == max(data$x)+1, select = 2:5),
subset(pred3, x == max(data$x)+1, select = 2:5),
subset(pred4, x == max(data$x)+1, select = 2:5))
print(pred, digits = 3)
## date fit lwr upr
## 53 2020-04-16 26996 22034 32260
## 531 2020-04-16 21003 20197 21536
## 532 2020-04-16 21846 21593 22171
## 533 2020-04-16 21929 21619 22316
ylim = c(0, max(pred2$upr, pred3$upr, na.rm=TRUE))ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(data = pred1, aes(x = date, y = fit, color = "Exponential")) +
geom_line(data = pred2, aes(x = date, y = fit, color = "Logistic")) +
geom_line(data = pred3, aes(x = date, y = fit, color = "Gompertz")) +
geom_line(data = pred4, aes(x = date, y = fit, color = "Richards")) +
geom_ribbon(data = pred1, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[1], alpha=0.3) +
geom_ribbon(data = pred2, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[2], alpha=0.3) +
geom_ribbon(data = pred3, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[3], alpha=0.3) +
geom_ribbon(data = pred4, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[4], alpha=0.3) +
coord_cartesian(ylim = c(0, max(ylim))) +
labs(x = "", y = "Deceased", color = "Model") +
scale_y_continuous(minor_breaks = seq(0, max(ylim), by = 1000)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
scale_color_manual(values = cols) +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))# create data for analysis
data = data.frame(date = COVID19$data,
y = COVID19$dimessi_guariti,
dy = reldiff(COVID19$dimessi_guariti))
data$x = as.numeric(data$date) - min(as.numeric(data$date)) + 1
DT::datatable(data, options = list("pageLength" = 5))mod1_start = lm(log(y) ~ x, data = data)
b = unname(coef(mod1_start))
start = list(th1 = exp(b[1]), th2 = b[2])
exponential <- function(x, th1, th2) th1 * exp(th2 * x)
mod1 = nls(y ~ exponential(x, th1, th2), data = data, start = start)
summary(mod1)
##
## Formula: y ~ exponential(x, th1, th2)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## th1 905.604738 90.105756 10.05 0.000000000000136 ***
## th2 0.073966 0.002152 34.37 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1639 on 50 degrees of freedom
##
## Number of iterations to convergence: 11
## Achieved convergence tolerance: 0.000007726mod2 = nls(y ~ SSlogis(x, Asym, xmid, scal), data = data)
summary(mod2)
##
## Formula: y ~ SSlogis(x, Asym, xmid, scal)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## Asym 53121.7312 1979.4494 26.84 <2e-16 ***
## xmid 44.4916 0.6758 65.83 <2e-16 ***
## scal 8.2178 0.2288 35.91 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 596.7 on 49 degrees of freedom
##
## Number of iterations to convergence: 0
## Achieved convergence tolerance: 0.000003242mod3 = nls(y ~ SSgompertz(x, Asym, b2, b3), data = data)
summary(mod3)
##
## Formula: y ~ SSgompertz(x, Asym, b2, b3)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## Asym 117256.287651 7825.639733 14.98 <2e-16 ***
## b2 8.829819 0.199398 44.28 <2e-16 ***
## b3 0.960928 0.001435 669.77 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 352.4 on 49 degrees of freedom
##
## Number of iterations to convergence: 0
## Achieved convergence tolerance: 0.000005849richards <- function(x, th1, th2, th3) th1*(1 - exp(-th2*x))^th3
Loss <- function(th, y, x) sum((y - richards(x, th[1], th[2], th[3]))^2)
start <- optim(par = c(coef(mod2)[1], 0.001, 1), fn = Loss,
y = data$y, x = data$x)$par
names(start) <- c("th1", "th2", "th3")
mod4 = nls(y ~ richards(x, th1, th2, th3), data = data, start = start,
# trace = TRUE, # algorithm = "port",
control = nls.control(maxiter = 1000))
summary(mod4)
##
## Formula: y ~ richards(x, th1, th2, th3)
##
## Parameters:
## Estimate Std. Error t value Pr(>|t|)
## th1 238985.442105 41753.326846 5.724 0.00000062181531 ***
## th2 0.020786 0.002246 9.254 0.00000000000247 ***
## th3 4.386103 0.224154 19.567 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 326.1 on 49 degrees of freedom
##
## Number of iterations to convergence: 17
## Achieved convergence tolerance: 0.000001563models = list("Exponential model" = mod1,
"Logistic model" = mod2,
"Gompertz model" = mod3,
"Richards model" = mod4)
tab = data.frame(loglik = sapply(models, logLik),
df = sapply(models, function(m) attr(logLik(m), "df")),
Rsquare = sapply(models, function(m)
cor(data$y, fitted(m))^2),
AIC = sapply(models, AIC),
AICc = sapply(models, AICc),
BIC = sapply(models, BIC))
sel <- apply(tab[,4:6], 2, which.min)
tab$"" <- sapply(tabulate(sel, nbins = length(models))+1, symnum,
cutpoints = 0:4, symbols = c("", "*", "**", "***"))
knitr::kable(tab)| loglik | df | Rsquare | AIC | AICc | BIC | ||
|---|---|---|---|---|---|---|---|
| Exponential model | -457.6527 | 3 | 0.9853646 | 921.3054 | 921.8054 | 927.1591 | |
| Logistic model | -404.5956 | 4 | 0.9979192 | 817.1912 | 818.0423 | 824.9962 | |
| Gompertz model | -377.2109 | 4 | 0.9991738 | 762.4218 | 763.2728 | 770.2268 | |
| Richards model | -373.1697 | 4 | 0.9992845 | 754.3394 | 755.1905 | 762.1444 | *** |
ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(aes(y = fitted(mod1), color = "Exponential")) +
geom_line(aes(y = fitted(mod2), color = "Logistic")) +
geom_line(aes(y = fitted(mod3), color = "Gompertz")) +
geom_line(aes(y = fitted(mod4), color = "Richards")) +
labs(x = "", y = "Recovered", color = "Model") +
scale_color_manual(values = cols) +
scale_y_continuous(breaks = seq(0, coef(mod2)[1], by = 1000),
minor_breaks = seq(0, coef(mod2)[1], by = 500)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))last_plot() +
scale_y_continuous(trans = "log10", limits = c(10,NA)) +
labs(y = "Recovered (log10 scale)")df = data.frame(x = seq(min(data$x), max(data$x)+14))
df = cbind(df, date = as.Date(df$x, origin = data$date[1]-1),
fit1 = predict(mod1, newdata = df),
fit2 = predict(mod2, newdata = df),
fit3 = predict(mod3, newdata = df),
fit4 = predict(mod4, newdata = df))
ylim = c(0, max(df[,-(1:3)]))ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(data = df, aes(x = date, y = fit1, color = "Exponential")) +
geom_line(data = df, aes(x = date, y = fit2, color = "Logistic")) +
geom_line(data = df, aes(x = date, y = fit3, color = "Gompertz")) +
geom_line(data = df, aes(x = date, y = fit4, color = "Richards")) +
coord_cartesian(ylim = ylim) +
labs(x = "", y = "Recovered", color = "Model") +
scale_y_continuous(breaks = seq(0, max(ylim), by = 1000),
minor_breaks = seq(0, max(ylim), by = 1000)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
scale_color_manual(values = cols) +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))# compute prediction using Moving Block Bootstrap (MBB) for nls
df = data.frame(x = seq(min(data$x), max(data$x)+14))
df = cbind(df, date = as.Date(df$x, origin = data$date[1]-1))
pred1 = cbind(df, "fit" = predict(mod1, newdata = df))
pred1[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod1, df[df$x > max(data$x),])[,2:3]
pred2 = cbind(df, "fit" = predict(mod2, newdata = df))
pred2[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod2, df[df$x > max(data$x),])[,2:3]
pred3 = cbind(df, "fit" = predict(mod3, newdata = df))
pred3[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod3, df[df$x > max(data$x),])[,2:3]
pred4 = cbind(df, "fit" = predict(mod4, newdata = df))
pred4[df$x > max(data$x), c("lwr", "upr")] = predictMBB.nls(mod4, df[df$x > max(data$x),])[,2:3]
# predictions for next day
pred = rbind(subset(pred1, x == max(data$x)+1, select = 2:5),
subset(pred2, x == max(data$x)+1, select = 2:5),
subset(pred3, x == max(data$x)+1, select = 2:5),
subset(pred4, x == max(data$x)+1, select = 2:5))
print(pred, digits = 3)
## date fit lwr upr
## 53 2020-04-16 45653 41073 50439
## 531 2020-04-16 39201 37272 40818
## 532 2020-04-16 40300 39245 41249
## 533 2020-04-16 40634 39796 41349
ylim = c(0, max(pred2$upr, pred3$upr, na.rm=TRUE))ggplot(data, aes(x = date, y = y)) +
geom_point() +
geom_line(data = pred1, aes(x = date, y = fit, color = "Exponential")) +
geom_line(data = pred2, aes(x = date, y = fit, color = "Logistic")) +
geom_line(data = pred3, aes(x = date, y = fit, color = "Gompertz")) +
geom_line(data = pred4, aes(x = date, y = fit, color = "Richards")) +
geom_ribbon(data = pred1, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[1], alpha=0.3) +
geom_ribbon(data = pred2, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[2], alpha=0.3) +
geom_ribbon(data = pred3, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[3], alpha=0.3) +
geom_ribbon(data = pred4, aes(x = date, ymin = lwr, ymax = upr),
inherit.aes = FALSE, fill = cols[4], alpha=0.3) +
coord_cartesian(ylim = c(0, max(ylim))) +
labs(x = "", y = "Recovered", color = "Model") +
scale_y_continuous(breaks = seq(0, max(ylim), by = 5000),
minor_breaks = seq(0, max(ylim), by = 1000)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
scale_color_manual(values = cols) +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))df = data.frame(date = COVID19$data,
positives = c(NA, diff(COVID19$totale_casi)),
swabs = c(NA, diff(COVID19$tamponi)))
df$x = as.numeric(df$date) - min(as.numeric(df$date)) + 1
# df$y = df$positives/df$swabs
df$y = df$positives/c(NA, zoo::rollmean(df$swabs, 2))
df = subset(df, swabs > 50)
# DT::datatable(df[,-4], )ggplot(df, aes(x = date)) +
geom_point(aes(y = swabs, color = "swabs"), pch = 19) +
geom_line(aes(y = swabs, color = "swabs")) +
geom_point(aes(y = positives, color = "positives"), pch = 0) +
geom_line(aes(y = positives, color = "positives")) +
labs(x = "", y = "Number of cases", color = "") +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
scale_color_manual(values = palette()[c(2,1)]) +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))ggplot(df, aes(x = date, y = y)) +
geom_smooth(method = "loess", se = TRUE, col = "black") +
geom_point(col=palette()[4]) +
geom_line(size = 0.5, col=palette()[4]) +
labs(x = "", y = "% positives among admnistered swabs (two-day rolling mean)") +
scale_y_continuous(labels = scales::percent_format(),
breaks = seq(0, 0.5, by = 0.05)) +
coord_cartesian(ylim = c(0,max(df$y, na.rm = TRUE))) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))df = data.frame(date = COVID19$data,
hospital = c(NA, diff(COVID19$totale_ospedalizzati)),
icu = c(NA, diff(COVID19$terapia_intensiva)))
df$x = as.numeric(df$date) - min(as.numeric(df$date)) + 1ggplot(df, aes(x = date, y = hospital)) +
geom_smooth(method = "loess", se = TRUE, col = "black") +
geom_point(col = "orange") +
geom_line(size = 0.5, col = "orange") +
labs(x = "", y = "Change hospitalized patients") +
coord_cartesian(ylim = range(df$hospital, na.rm = TRUE)) +
scale_y_continuous(minor_breaks = seq(min(df$hospital, na.rm = TRUE),
max(df$hospital, na.rm = TRUE),
by = 100)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))ggplot(df, aes(x = date, y = icu)) +
geom_smooth(method = "loess", se = TRUE, col = "black") +
geom_point(col = "red2") +
geom_line(size = 0.5, col = "red2") +
labs(x = "", y = "Change ICU patients") +
coord_cartesian(ylim = range(df$icu, na.rm = TRUE)) +
scale_y_continuous(minor_breaks = seq(min(df$icu, na.rm = TRUE),
max(df$icu, na.rm = TRUE),
by = 10)) +
scale_x_date(date_breaks = "2 day", date_labels = "%b%d",
minor_breaks = "1 day") +
theme_bw() +
theme(legend.position = "top",
axis.text.x = element_text(angle=60, hjust=1))